medical.egfr

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond what readOnlyHint, idempotentHint and openWorldHint already cover, the description discloses output units (mL/min/1.73m²), the rounding rule (HALF_EVEN to one decimal), and the subtle ordering rule that staging is computed from the rounded value. It also explicitly documents that the race parameter is ignored, which is real behavioral substance an agent could not infer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and equation, then inputs, then output semantics, then exclusions. Each sentence adds information that is not repeated elsewhere, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and 4 parameters at 0% schema coverage, this description supplies everything needed to call the tool correctly: units, types, rounding, staging rule, ignored parameter, and applicability limits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does: creatinine is specified as an mg/dL Decimal string, age as an integer, sex as male|female, and race as accepted-but-ignored. Every one of the four parameters gets meaning that the bare schema does not provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb and resource (estimating eGFR from serum creatinine) together with the exact equation (CKD-EPI 2021, race-free) and the derived output (KDIGO 2012 stage G1-G5). The clinical scope makes it trivially distinguishable from siblings such as medical.bmi or medical.bsa without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly states the input domain (mg/dL Decimal string, integer age, sex=male|female) and gives explicit exclusions: it cannot be used for cystatin C-based or pediatric equations. That is strong when-not guidance, but it does not name an alternative tool for those cases, so it falls short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.